ModelPrésentéExterne

Ddpm Cifar10 32 Dot.in.name

Paper: Denoising Diffusion Probabilistic Models

Sourcehuggingface.co/akasharidas/ddpm-cifar10-32-dot.in.name/tree/39fee3d79d5c44c21ca5b58a6363d5bc78bbd8cf

TypeOtherVersionRevision 39fee3dBClasse

Source du modèle

Type: Other
Taille du fichier: 136 MB
Version: vRevision 39fee3d
Mis à jour: 27 sept. 2026
Téléchargements: 8 k
Source: Hugging Face

Description de la source

Denoising Diffusion Probabilistic Models (DDPM)

Paper: Denoising Diffusion Probabilistic Models

Authors: Jonathan Ho, Ajay Jain, Pieter Abbeel

Abstract:

We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.

Inference

DDPM models can use discrete noise schedulers such as:

for inference. Note that while the ddpm scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the ddim or pndm schedulers instead.

See the following code:

# !pip install diffusers
from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline

model_id = "google/ddpm-cifar10-32"

# load model and scheduler
ddpm = DDPMPipeline.from_pretrained(model_id)  # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference

# run pipeline in inference (sample random noise and denoise)
image = ddpm().images[0]

# save image
image.save("ddpm_generated_image.png")

For more in-detail information, please have a look at the official inference example

Training

If you want to train your own model, please have a look at the official training example

Samples

sample_1
sample_2
sample_3
sample_4

Sources

1 source

Hugging FacePrincipalVersion 39fee3d79d5c44c21ca5b58a6363d5bc78bbd8cf

huggingface.co/akasharidas/ddpm-cifar10-32-dot.in.name/tree/39fee3d79d5c44c21ca5b58a6363d5bc78bbd8cf

Vérifié 8 sept.

Artefacts du modèle

2 artefacts

diffusion_pytorch_model.bin

bin · 136 MB · SHA-256 ac3416a54887…8ea4 · Hugging Face

Télécharger

diffusion_pytorch_model.safetensors

safetensors · 136 MB · SHA-256 1558dbe3fb09…9f0f · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme8 sept.huggingface.co/akasharidas/ddpm-cifar10-32-dot.in.name

--- license: apache-2.0 tags: - pytorch - diffusers - unconditional-image-generation --- # Denoising Diffusion Probabilistic Models (DDPM) **Paper**: [Denoising Diffusion Probabilistic Models](https://arxiv.org/abs/2006.11239) **Authors**: Jonathan Ho, Ajay Jain, Pieter Abbeel **Abstract**: *We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN.* ## Inference **DDPM** models can use *discrete noise schedulers* such as: - [scheduling_ddpm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddpm.py) - [scheduling_ddim](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_ddim.py) - [scheduling_pndm](https://github.com/huggingface/diffusers/blob/main/src/diffusers/schedulers/scheduling_pndm.py) for inference. Note that while the *ddpm* scheduler yields the highest quality, it also takes the longest. For a good trade-off between quality and inference speed you might want to consider the *ddim* or *pndm* schedulers instead. See the following code: ```python # !pip install diffusers from diffusers import DDPMPipeline, DDIMPipeline, PNDMPipeline model_id = "google/ddpm-cifar10-32" # load model and scheduler ddpm = DDPMPipeline.from_pretrained(model_id) # you can replace DDPMPipeline with DDIMPipeline or PNDMPipeline for faster inference # run pipeline in inference (sample random noise and denoise) image = ddpm().images[0] # save image image.save("ddpm_generated_image.png") ``` For more in-detail information, please have a look at the [official inference example](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/diffusers_intro.ipynb) ## Training If you want to train your own model, please ha...

Note8 sept.huggingface.co/akasharidas/ddpm-cifar10-32-dot.in.name

Source context: 7990 downloads · 0 likes · Pipeline unconditional-image-generation · Library diffusers · Repo akasharidas/ddpm-cifar10-32-dot.in.name